charm AT lists.siebelschool.illinois.edu

Subject: Charm++ parallel programming system

List archive

[charm] Charm++ and TAU

From: Laércio Lima Pilla <llpilla AT inf.ufrgs.br>
To: Charm Mailing List <charm AT cs.illinois.edu>
Subject: [charm] Charm++ and TAU
Date: Tue, 30 Oct 2012 14:20:26 +0100
List-archive: <http://lists.cs.uiuc.edu/pipermail/charm/>
List-id: CHARM parallel programming system <charm.cs.uiuc.edu>

Hi,

I was planning to generate TAU traces with Charm++ benchmarks (such as kneighbor and leanmd) so I could translate them to paje traces.

So far, I have only found information about using TAU with NAMD ( http://www.nic.uoregon.edu/tau-wiki/Guide:NAMDTAU ), AMPI (from Xoan emails in this list), and the ICPP paper.

I would like to know if there are any restrictions on using TAU without any MPI or using the shared memory build of Charm++. Which parameters would have to be added when building Charm, when compiling the application, and when running the application?

Best regards,

Laércio LIMA PILLA

PhD Student at

- Federal University of Rio Grande do Sul (UFRGS) - Brazil

- Grenoble University - France
Email: laercio.pilla AT inf.ufrgs.br or laercio.lima.pilla AT gmail.com
Tel: +33 (0)6 49 87 68 29
Website: www.inf.ufrgs.br/~llpilla

[charm] Charm++ and TAU, Laércio Lima Pilla, 10/30/2012